Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

TL;DR

This paper introduces MCRN, a novel framework for unsupervised domain adaptive person re-identification that uses multiple centroids, domain-specific contrastive learning, and second-order interpolation to improve clustering and feature discrimination.

Contribution

The paper proposes a Multi-Centroid Memory (MCM) and two strategies, DSCL and SONI, to enhance contrastive learning and handle label noise in UDA re-ID tasks, advancing the state-of-the-art.

Findings

MCRN outperforms existing methods on multiple UDA re-ID benchmarks.

MCM effectively mitigates label noise within clusters.

DSCL and SONI improve the quality of positive and negative samples.

Abstract

Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks.